Pitcher Precision

Last Update: 2019-05-01 16:02:25

Libraries

Let’s load some libraries in first.

library(baseballr)
library(pitchRx)
library(tidyverse)

Let’s also clean out environment.

rm(list = ls())

With these libraries, we can get out data as well as visaulize it. Let’s take a look at some players to see what we can look at.

Data Loading

Here are the list of players I will be looking at.

Noah Syndergaard - Player ID: 592789
Patrick Corbin - Player ID: 571578
Felipe Vazquez - Player ID: 553878
Marcus Stroman - Player ID: 573186
Justin Verlander - Player ID: 434378
Blake Treinen - Player ID: 595014

Let’s now scrape the data for each player.

scrape.data = function(start, id) {
    data = scrape_statcast_savant(start_date = start,
                                  end_date = "2019-04-22",
                                  playerid = id,
                                  player_type = 'pitcher')
    data
}

start = "2019-01-01"

syndergaard.data = scrape.data(start, 592789)
corbin.data = scrape.data(start, 571578)
vazquez.data = scrape.data(start, 553878)
stroman.data = scrape.data(start, 573186)
verlander.data = scrape.data(start, 434378)
treinen.data = scrape.data(start, 595014)

Now with our data, let’s get the information we want out of it.

filter.data = function(data) {
    filtered = data.frame(name = data %>% pull(player_name),
                          pitch = data %>% pull(pitch_type),
                          outcome = data %>% pull(type),
                          date = data %>% pull(game_date),
                          event = data %>% pull(events),
                          descrip = data %>% pull(description),
                          xcoord = data %>% pull(plate_x),
                          ycoord = data %>% pull(plate_z),
                          xmove = data %>% pull(pfx_x),
                          ymove = data %>% pull(pfx_z),
                          velo = data %>% pull(effective_speed),
                          spin = data %>% pull(release_spin_rate),
                          exvelo = data %>% pull(launch_speed),
                          exang = data %>% pull(launch_angle))
    filtered
}

syndergaard = filter.data(syndergaard.data)
corbin = filter.data(corbin.data)
stroman = filter.data(stroman.data)
treinen = filter.data(treinen.data)
vazquez = filter.data(vazquez.data)
verlander = filter.data(verlander.data)

With this filtered data, we have selected the following columns:

Name
Pitch type
Pitch outcome (Strike, Ball, In play)
Game Date
Event
Description of event
X coordinate (horizontal location) of pitch
Y coordinate (vertical location) of pitch
Horizontal movement (X coordinate movement) of pitch
Vertical movement (Y coordinate movement) of pitch
Velocity of pitch
Spin rate of pitch
Exit velocity of pitch
Launch angle of pitch

Visualization

Let’s start visualizing some of this data. Before that, let me define a strikezone. This strikezone was taken from the website Baseball with R

topKzone = 3.5
botKzone = 1.6
inKzone = -.95
outKzone = 0.95
kZone = data.frame(x = c(inKzone, inKzone, outKzone, outKzone, inKzone),
                   y = c(botKzone, topKzone, topKzone, botKzone, botKzone))

Pitch Location via Pitch Type

Let’s look at pitch location via pitch type.

graph.pitch.heatmap.type = function(player) {
    graph = ggplot(player) +
        geom_jitter(aes(x = player$xcoord,
                        y = player$ycoord,
                        color = player$pitch)) +
        xlab("Horizontal Position") +
        ylab("Vertical Position") +
        ggtitle(paste(player$name[1], "Heatmap", sep = " ")) +
        labs(color = "Pitch Type") +
        theme_minimal() + geom_path(aes(x, y), data = kZone)
    graph
}

corbin.heatmap.type = graph.pitch.heatmap.type(corbin)
corbin.heatmap.type

stroman.heatmap.type = graph.pitch.heatmap.type(stroman)
stroman.heatmap.type

syndergaard.heatmap.type = graph.pitch.heatmap.type(syndergaard)
syndergaard.heatmap.type

## Warning: Removed 1 rows containing missing values (geom_point).

treinen.heatmap.type = graph.pitch.heatmap.type(treinen)
treinen.heatmap.type

## Warning: Removed 23 rows containing missing values (geom_point).

vazquez.heatmap.type = graph.pitch.heatmap.type(vazquez)
vazquez.heatmap.type

verlander.heatmap.type = graph.pitch.heatmap.type(verlander)
verlander.heatmap.type

Pitch Location via Velocity

Let’s look at pitch location via velocity.

graph.pitch.heatmap.velo = function(player.data) {
    graph = ggplot(player.data) +
        geom_jitter(aes(x = player.data$xcoord,
                        y = player.data$ycoord,
                        color = player.data$velo)) +
        xlab("Horizontal Position") +
        ylab("Vertical Position") +
        ggtitle(paste(player.data$name[1], "Heatmap", sep = " ")) +
        labs(color = "Velocity") +
        scale_color_gradient(low = "blue", high = "red") +
        theme_minimal() + geom_path(aes(x, y), data = kZone)
    graph
}

corbin.heatmap.velo = graph.pitch.heatmap.velo(corbin)
corbin.heatmap.velo

stroman.heatmap.velo = graph.pitch.heatmap.velo(stroman)
stroman.heatmap.velo

syndergaard.heatmap.velo = graph.pitch.heatmap.velo(syndergaard)
syndergaard.heatmap.velo

## Warning: Removed 1 rows containing missing values (geom_point).

treinen.heatmap.velo = graph.pitch.heatmap.velo(treinen)
treinen.heatmap.velo

## Warning: Removed 23 rows containing missing values (geom_point).

vazquez.heatmap.velo = graph.pitch.heatmap.velo(vazquez)
vazquez.heatmap.velo

verlander.heatmap.velo = graph.pitch.heatmap.velo(verlander)
verlander.heatmap.velo

Pitch Movement

To view the movement, let’s just determine the average movement for each type of pitch that each player has. First let’s make a few helpful functions for us.

graph.pitch.xmovement = function(player) {
    graph = ggplot(player) +
        geom_boxplot(aes(x = player$pitch,
                         y = player$xmove,
                         color = player$pitch)) +
        coord_flip() +
        labs(color = "Pitch Type") +
        xlab("Pitch Type") + ylab("Horizontal Movement") +
        ggtitle(paste(player$name[1], "Horizontal Movement", sep = " ")) +
        theme_minimal()
}

graph.pitch.ymovement = function(player) {
    graph = ggplot(player) +
        geom_boxplot(aes(x = player$pitch,
                         y = player$ymove,
                         color = player$pitch)) +
        labs(color = "Pitch Type") +
        xlab("Pitch Type") + ylab("Vertical Movement") +
        ggtitle(paste(player$name[1], "Vertical Movement", sep = " ")) +
        theme_minimal()
}

Patrick Corbin

corbin.xmove = graph.pitch.xmovement(corbin)
corbin.ymove = graph.pitch.ymovement(corbin)
corbin.xmove

corbin.ymove

Marcus Stroman

stroman.xmove = graph.pitch.xmovement(stroman)
stroman.ymove = graph.pitch.ymovement(stroman)
stroman.xmove

stroman.ymove

Noah Syndergaard

syndergaard.xmove = graph.pitch.xmovement(syndergaard)
syndergaard.ymove = graph.pitch.ymovement(syndergaard)
syndergaard.xmove

## Warning: Removed 1 rows containing non-finite values (stat_boxplot).

syndergaard.ymove

## Warning: Removed 1 rows containing non-finite values (stat_boxplot).

Blake Treinen

treinen.xmove = graph.pitch.xmovement(treinen)
treinen.ymove = graph.pitch.ymovement(treinen)
treinen.xmove

## Warning: Removed 23 rows containing non-finite values (stat_boxplot).

treinen.ymove

## Warning: Removed 23 rows containing non-finite values (stat_boxplot).

Felipe Vazquez

vazquez.xmove = graph.pitch.xmovement(vazquez)
vazquez.ymove = graph.pitch.ymovement(vazquez)
vazquez.xmove

vazquez.ymove

Justin Verlander

verlander.xmove = graph.pitch.xmovement(verlander)
verlander.ymove = graph.pitch.ymovement(verlander)
verlander.xmove

verlander.ymove

Pitch Velocity

We need to separate each pitch first by type. Then we can see how the pitch’s velocity changed over time.

graph.pitch.velo = function(player) {
    graph = ggplot(player) +
        geom_line(aes(x = 1:length(player$velo),
                      y = player$velo,
                      color = player$pitch)) +
        xlab("Pitches Thrown") + ylab("Velocity") + labs(color = "Pitch Type") +
        ggtitle(paste(player$name[1], "Pitch Velocity Chart", sep = " ")) +
        theme_minimal()
}

corbin.velo = graph.pitch.velo(corbin)
corbin.velo

stroman.velo = graph.pitch.velo(stroman)
stroman.velo

syndergaard.velo = graph.pitch.velo(syndergaard)
syndergaard.velo

## Warning: Removed 1 rows containing missing values (geom_path).

treinen.velo = graph.pitch.velo(treinen)
treinen.velo

## Warning: Removed 23 rows containing missing values (geom_path).

vazquez.velo = graph.pitch.velo(vazquez)
vazquez.velo

verlander.velo = graph.pitch.velo(verlander)
verlander.velo

Pitch Spin Rate

graph.pitch.spin = function(player) {
    graph = ggplot(player) +
        geom_step(aes(x = 1:length(player$spin),
                      y = player$spin,
                      color = player$pitch),
                  direction = "vh") +
        xlab("Pitches Thrown") + ylab("Spin Rate") + labs(color = "Pitch Type") +
        ggtitle(paste(player$name[1], "Pitch Spin Rate Chart", sep = " ")) +
        theme_minimal()
}

corbin.spin = graph.pitch.spin(corbin)
corbin.spin

stroman.spin = graph.pitch.spin(stroman)
stroman.spin

syndergaard.spin = graph.pitch.spin(syndergaard)
syndergaard.spin

## Warning: Removed 1 rows containing missing values (geom_path).

treinen.spin = graph.pitch.spin(treinen)
treinen.spin

## Warning: Removed 23 rows containing missing values (geom_path).

vazquez.spin = graph.pitch.spin(vazquez)
vazquez.spin

verlander.spin = graph.pitch.spin(verlander)
verlander.spin

Analysis

I’ll be looking at a few specific Pittsburgh Pirates pitchers and looking at them from year to year.

Pitcher Precision

Sasank Vishnubhatla

4/17/2019